2 papers
cs.CV2026
Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning
Chenyang Wu, Fuchen Long, Binyuan Huang +4
While generative AI has significantly advanced video editing, existing methods primarily focus on single-shot or short video clips. Editing long videos with multiple instructions r…
cs.CV2026
Déjà Cue: Localizing States in Object Histories via Vocabulary-Relative Coordinates
Haofan Cao, Zhichao You, Yunkai Yang +3
Tracking links observations of the same object through visual change, yet cannot by itself determine when the object is empty or filled, intact or cut. We formulate identity-condit…